Qwen3 30B A3B Thinking 2507
by Alibaba (Qwen) · qwen/qwen3-30b-a3b-thinking-2507 · #203 cheapest of 422 paid models
Prices updated Sep 19, 2026, 6:21 PM UTC · refreshed hourly
Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.20
per 1M tokens
Output
$2.40
per 1M tokens
Blended (3:1)
$0.75
3 input : 1 output
Cache read
—
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Qwen3 30B A3B Thinking 2507 (no cache-read rate published — hits billed as normal input).
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.75 | $0.0228 | — |
| 50% | $0.75 | $0.0228 | −0% |
| 90% | $0.75 | $0.0228 | −0% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.00082 | $0.82 |
| Document summary | 8,000 | 1,000 | $0.004 | $4.00 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0108 | $10.80 |
| Long-context analysis | 150,000 | 5,000 | $0.042 | $42.00 |
Performance
Intelligence Index
9.8
AA composite quality
Coding Index
12.1
Math Index
—
Agentic Index
0.9
Output speed
—
median
Time to first token
—
median
Time to first answer
—
after reasoning tokens
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 943 |
| Data viz | 939 |
Specs
Context window
82K
tokens
Max output
33K
tokens
Input modalities
text
Tokenizer
Qwen3